Zhibo Wang
4 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces LoopTrap, an automated red-teaming framework that demonstrates how malicious prompts can poison the termination judgment of LLM agents, causing unbounded computation.
RouteScan introduces a non-intrusive framework that audits the safety of Mixture-of-Experts (MoE) LLMs by analyzing low-level GPU expert routing telemetry, achieving high accuracy even on unseen harmful prompts.
LoRA-Key introduces a user-centric watermarking framework that attaches a recoverable ownership key to LoRA modules via a standalone Watermark LoRA, providing lightweight, plug-and-play copyright protection without requiring per-LoRA retraining.
This paper reveals a new vulnerability in Language Model (LLM) inference efficiency caused by persona consistency and proposes RolePlay, a framework to amplify inference costs.
Papers
From Role Prompt to Infinite Thinking: Exploiting Persona Conditioning for Inference Cost Attacks in LLMs
Zhiyi Mou, Wangze Ni, Tianfang Xiao, Haoyang LI +5 more
This paper reveals a new vulnerability in Language Model (LLM) inference efficiency caused by persona consistency and proposes RolePlay, a framework to amplify inference costs.